AI Paper Atlas

Research map / Label-efficient and robust learning / Knowledge distillation

Cross-Architecture Distillation Made Simple with Redundancy Suppression

Weijia Zhang, Yuehao Liu, Wu Ran, Chao Ma

ICCV 2025 · Label-efficient and robust learning › Knowledge distillation · approach: Rethinking distillation objectives · 11 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add decorrelation (off-diagonal) objective to invariance objective (ablation)RSD · CIFAR-100 (Swin-T to ResNet18)accuracy: 80.65 -> 83.92Improved
add decorrelation objective to invariance objective (ablation)RSD · CIFAR-100 (ConvNeXt-T to ResMLP-S12)accuracy: 83.40 -> 84.21Improved
add RSD invariance objective over no distillation (ablation)student · CIFAR-100 (Swin-T to ResNet18)accuracy: 74.01 -> 80.65Improved
add AAD decoupler module (ablation)RSD · CIFAR-100 (ViT-S to ResMLP-S12)accuracy: 82.26 -> 82.94Improved
add AAD decoupler module (ablation)RSD · ImageNet-1k (ConvNeXt-T to Mixer-B/16)accuracy: 79.93 -> 80.73Improved
use RSD loss on logits instead of OFA logit loss (ablation)logit distillation · CIFAR-100 (Mixer-B/16 to DeiT-T)accuracy: 70.69 -> 77.22Improved
use RSD loss on logits instead of KD loss (ablation)logit distillation · CIFAR-100 (Swin-T to ResNet18)accuracy: 78.74 -> 83.23Improved
replace OFA losses with RSD loss (OFA+RSD) (ablation)OFA · CIFAR-100 (ConvNeXt-T to ResMLP-S12)accuracy: 81.22 -> 84.46Improved
replace OFA losses with RSD loss (OFA+RSD) (ablation)OFA · ImageNet-1k (DeiT-T to ResNet18)accuracy: 70.64 -> 71.21Improved
add RSD over OFA-projected intermediate features at stages {1,2,3,4} (ablation)RSD · CIFAR-100 (Swin-T to ResNet18)accuracy: 83.92 -> 85.45Improved
add RSD over OFA-projected intermediate features at stages {3,4} (ablation)RSD · CIFAR-100 (Mixer-B/16 to DeiT-T)accuracy: 76.45 -> 76.37No clear effect
use RSD instead of OFA in cross-architecture distillationstudent · CIFAR-100 (ConvNeXt-T to DeiT-T)accuracy: 75.76 -> 82.46Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy